[RFC Part1 PATCH v3 00/17] x86: Secure Encrypted Virtualization (AMD)

@@ -1,4 +1,5 @@
-Secure Memory Encryption (SME) is a feature found on AMD processors.
+Secure Memory Encryption (SME) and Secure Encrypted Virtualization (SEV) are
+features found on AMD processors.
 
 SME provides the ability to mark individual pages of memory as encrypted using
 the standard x86 page tables.  A page that is marked encrypted will be

@@ -6,6 +7,12 @@ automatically decrypted when read from DRAM and encrypted when written to
 DRAM.  SME can therefore be used to protect the contents of DRAM from physical
 attacks on the system.
 
+SEV enables running encrypted virtual machine (VMs) in which the code and data
+of the virtual machine are secured so that decrypted version is available only
+within the VM itself. SEV guest VMs have concept of private and shared memory.
+Private memory is encrypted with the guest-specific key, while shared memory
+may be encrypted with hypervisor key.
+
 A page is encrypted when a page table entry has the encryption bit set (see
 below on how to determine its position).  The encryption bit can also be
 specified in the cr3 register, allowing the PGD table to be encrypted. Each

@@ -19,11 +26,20 @@ so that the PGD is encrypted, but not set the encryption bit in the PGD entry
 for a PUD which results in the PUD pointed to by that entry to not be
 encrypted.
 
-Support for SME can be determined through the CPUID instruction. The CPUID
-function 0x8000001f reports information related to SME:
+When SEV is enabled, certain type of memory (namely insruction pages and guest
+page tables) are always treated as private. Due to security reasons all DMA
+operations inside the guest must be performed on shared memory. Since the
+memory encryption bit is only controllable by the guest OS when it is operating
+in 64-bit or 32-bit PAE mode, in all other modes the SEV hardware forces memory
+encryption bit to 1.
+
+Support for SME and SEV can be determined through the CPUID instruction. The
+CPUID function 0x8000001f reports information related to SME:
 
 	0x8000001f[eax]:
 		Bit[0] indicates support for SME
+	0x800001f[eax]:
+		Bit[1] indicates support for SEV
 	0x8000001f[ebx]:
 		Bits[5:0]  pagetable bit number used to activate memory
 			   encryption

@@ -39,6 +55,13 @@ determine if SME is enabled and/or to enable memory encryption:
 		Bit[23]   0 = memory encryption features are disabled
 			  1 = memory encryption features are enabled
 
+If SEV is supported, MSR 0xc0010131 (MSR_F17H_SEV) can be used to determine if
+SEV is active:
+
+	0xc0010131:
+		Bit[0]	  0 = memory encryption is not active
+			  1 = memory encryption is active
+
 Linux relies on BIOS to set this bit if BIOS has determined that the reduction
 in the physical address space as a result of enabling memory encryption (see
 CPUID information above) will not conflict with the address space resource

@@ -22,6 +22,7 @@
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
 extern unsigned long sme_me_mask;
+extern unsigned int sev_enabled;
 
 void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr,
 			 unsigned long decrypted_kernel_vaddr,

@@ -50,6 +51,7 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size);
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask	0UL
+#define sev_enabled	0
 
 static inline void __init sme_early_encrypt(resource_size_t paddr,
 					    unsigned long size) { }

@@ -40,6 +40,9 @@ static char sme_cmdline_off[] __initdata = "off";
 unsigned long sme_me_mask __section(.data) = 0;
 EXPORT_SYMBOL_GPL(sme_me_mask);
 
+unsigned int sev_enabled __section(.data) = 0;
+EXPORT_SYMBOL_GPL(sev_enabled);
+
 /* Buffer used for early in-place encryption by BSP, no locking needed */
 static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE);
 

@@ -22,12 +22,18 @@
 #else	/* !CONFIG_ARCH_HAS_MEM_ENCRYPT */
 
 #define sme_me_mask	0UL
+#define sev_enabled	0
 
 #endif	/* CONFIG_ARCH_HAS_MEM_ENCRYPT */
 
 static inline bool sme_active(void)
 {
-	return !!sme_me_mask;
+	return (sme_me_mask && !sev_enabled);
+}
+
+static inline bool sev_active(void)
+{
+	return (sme_me_mask && sev_enabled);
 }
 
 static inline unsigned long sme_get_me_mask(void)

@@ -197,6 +197,7 @@
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV		( 7*32+11) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */

@@ -378,6 +378,8 @@
 #define MSR_K7_PERFCTR3			0xc0010007
 #define MSR_K7_CLK_CTL			0xc001001b
 #define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT		0
+#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 

@@ -618,11 +618,16 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
 	/*
-	 * BIOS support is required for SME. If BIOS has enabled SME then
-	 * adjust x86_phys_bits by the SME physical address space reduction
-	 * value. If BIOS has not enabled SME then don't advertise the
-	 * feature (set in scattered.c). Also, since the SME support requires
-	 * long mode, don't advertise the feature under CONFIG_X86_32.
+	 * BIOS support is required for SME and SEV.
+	 *   For SME: If BIOS has enabled SME then adjust x86_phys_bits by
+	 *	      the SME physical address space reduction value.
+	 *	      If BIOS has not enabled SME then don't advertise the
+	 *	      SME feature (set in scattered.c).
+	 *   For SEV: If BIOS has not enabled SEV then don't advertise the
+	 *            SEV feature (set in scattered.c).
+	 *
+	 *   In all cases, since support for SME and SEV requires long mode,
+	 *   don't advertise the feature under CONFIG_X86_32.
 	 */
 	if (cpu_has(c, X86_FEATURE_SME)) {
 		u64 msr;

@@ -637,6 +642,21 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 			clear_cpu_cap(c, X86_FEATURE_SME);
 		}
 	}
+
+	if (cpu_has(c, X86_FEATURE_SEV)) {
+		if (IS_ENABLED(CONFIG_X86_32)) {
+			clear_cpu_cap(c, X86_FEATURE_SEV);
+		} else {
+			u64 syscfg, hwcr;
+
+			/* Check if SEV is enabled */
+			rdmsrl(MSR_K8_SYSCFG, syscfg);
+			rdmsrl(MSR_K7_HWCR, hwcr);
+			if (!(syscfg & MSR_K8_SYSCFG_MEM_ENCRYPT) ||
+			    !(hwcr & MSR_K7_HWCR_SMMLOCK))
+				clear_cpu_cap(c, X86_FEATURE_SEV);
+		}
+	}
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)

@@ -32,6 +32,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_CPB,		CPUID_EDX,  9, 0x80000007, 0 },
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
 	{ X86_FEATURE_SME,		CPUID_EAX,  0, 0x8000001f, 0 },
+	{ X86_FEATURE_SEV,		CPUID_EAX,  1, 0x8000001f, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 

@@ -379,9 +379,11 @@ static void __init reserve_initrd(void)
 	 * If SME is active, this memory will be marked encrypted by the
 	 * kernel when it is accessed (including relocation). However, the
 	 * ramdisk image was loaded decrypted by the bootloader, so make
-	 * sure that it is encrypted before accessing it.
+	 * sure that it is encrypted before accessing it. For SEV the
+	 * ramdisk will already be encyrpted, so only do this for SME.
 	 */
-	sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
+	if (sme_active())
+		sme_early_encrypt(ramdisk_image, ramdisk_end - ramdisk_image);
 
 	initrd_start = 0;
 

@@ -32,6 +32,7 @@
 #include <linux/reboot.h>
 #include <linux/slab.h>
 #include <linux/ucs2_string.h>
+#include <linux/mem_encrypt.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>

@@ -369,7 +370,10 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	 * as trim_bios_range() will reserve the first page and isolate it away
 	 * from memory allocators anyway.
 	 */
-	if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) {
+	pf = _PAGE_RW;
+	if (sev_active())
+		pf |= _PAGE_ENC;
+	if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, pf)) {
 		pr_err("Failed to create 1:1 mapping for the first page!\n");
 		return 1;
 	}

@@ -412,6 +416,9 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va)
 	if (!(md->attribute & EFI_MEMORY_WB))
 		flags |= _PAGE_PCD;
 
+	if (sev_active())
+		flags |= _PAGE_ENC;
+
 	pfn = md->phys_addr >> PAGE_SHIFT;
 	if (kernel_map_pages_in_pgd(pgd, pfn, va, md->num_pages, flags))
 		pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",

@@ -511,6 +518,9 @@ static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
 	pgd_t *pgd = efi_pgd;
 	int err1, err2;
 
+	if (sev_active())
+		pf |= _PAGE_ENC;
+
 	/* Update the 1:1 mapping */
 	pfn = md->phys_addr >> PAGE_SHIFT;
 	err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf);

@@ -589,6 +599,9 @@ void __init efi_runtime_update_mappings(void)
 			(md->type != EFI_RUNTIME_SERVICES_CODE))
 			pf |= _PAGE_RW;
 
+		if (sev_active())
+			pf |= _PAGE_ENC;
+
 		efi_update_mappings(md, pf);
 	}
 }

@@ -1781,8 +1781,8 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	unsigned long start;
 	int ret;
 
-	/* Nothing to do if the SME is not active */
-	if (!sme_active())
+	/* Nothing to do if SME and SEV are not active */
+	if (!sme_active() && !sev_active())
 		return 0;
 
 	/* Should not be working on unaligned addresses */

@@ -422,6 +422,9 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
  * areas should be mapped decrypted. And since the encryption key can
  * change across reboots, persistent memory should also be mapped
  * decrypted.
+ *
+ * If SEV is active, that implies that BIOS/UEFI also ran encrypted so
+ * only persistent memory should be mapped decrypted.
  */
 static bool memremap_should_map_decrypted(resource_size_t phys_addr,
 					  unsigned long size)

@@ -458,6 +461,11 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr,
 	case E820_TYPE_ACPI:
 	case E820_TYPE_NVS:
 	case E820_TYPE_UNUSABLE:
+		/* For SEV, these areas are encrypted */
+		if (sev_active())
+			break;
+		/* Fallthrough */
+
 	case E820_TYPE_PRAM:
 		return true;
 	default:

@@ -581,7 +589,7 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
 bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
 				 unsigned long flags)
 {
-	if (!sme_active())
+	if (!sme_active() && !sev_active())
 		return true;
 
 	if (flags & MEMREMAP_ENC)

@@ -590,10 +598,15 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
 	if (flags & MEMREMAP_DEC)
 		return false;
 
-	if (memremap_is_setup_data(phys_addr, size) ||
-	    memremap_is_efi_data(phys_addr, size) ||
-	    memremap_should_map_decrypted(phys_addr, size))
-		return false;
+	if (sme_active()) {
+		if (memremap_is_setup_data(phys_addr, size) ||
+		    memremap_is_efi_data(phys_addr, size) ||
+		    memremap_should_map_decrypted(phys_addr, size))
+			return false;
+	} else if (sev_active()) {
+		if (memremap_should_map_decrypted(phys_addr, size))
+			return false;
+	}
 
 	return true;
 }

@@ -608,15 +621,22 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
 					     unsigned long size,
 					     pgprot_t prot)
 {
-	if (!sme_active())
+	if (!sme_active() && !sev_active())
 		return prot;
 
-	if (early_memremap_is_setup_data(phys_addr, size) ||
-	    memremap_is_efi_data(phys_addr, size) ||
-	    memremap_should_map_decrypted(phys_addr, size))
-		prot = pgprot_decrypted(prot);
-	else
-		prot = pgprot_encrypted(prot);
+	if (sme_active()) {
+		if (early_memremap_is_setup_data(phys_addr, size) ||
+		    memremap_is_efi_data(phys_addr, size) ||
+		    memremap_should_map_decrypted(phys_addr, size))
+			prot = pgprot_decrypted(prot);
+		else
+			prot = pgprot_encrypted(prot);
+	} else if (sev_active()) {
+		if (memremap_should_map_decrypted(phys_addr, size))
+			prot = pgprot_decrypted(prot);
+		else
+			prot = pgprot_encrypted(prot);
+	}
 
 	return prot;
 }

@@ -63,9 +63,11 @@ static void __init setup_real_mode(void)
 	/*
 	 * If SME is active, the trampoline area will need to be in
 	 * decrypted memory in order to bring up other processors
-	 * successfully.
+	 * successfully. For SEV the trampoline area needs to be in
+	 * encrypted memory, so only do this for SME.
 	 */
-	set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT);
+	if (sme_active())
+		set_memory_decrypted((unsigned long)base, size >> PAGE_SHIFT);
 
 	memcpy(base, real_mode_blob, size);
 

@@ -397,9 +397,30 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc,
 		res->start = p->start;
 	if (res->end > p->end)
 		res->end = p->end;
+	res->desc = p->desc;
 	return 0;
 }
 
+static int __walk_iomem_res_desc(struct resource *res, unsigned long desc,
+				 bool first_level_children_only,
+				 void *arg, int (*func)(u64, u64, void *))
+{
+	u64 orig_end = res->end;
+	int ret = -1;
+
+	while ((res->start < res->end) &&
+	       !find_next_iomem_res(res, desc, first_level_children_only)) {
+		ret = (*func)(res->start, res->end, arg);
+		if (ret)
+			break;
+
+		res->start = res->end + 1;
+		res->end = orig_end;
+	}
+
+	return ret;
+}
+
 /*
  * Walks through iomem resources and calls func() with matching resource
  * ranges. This walks through whole tree and not just first level children.

@@ -418,26 +439,12 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
 		u64 end, void *arg, int (*func)(u64, u64, void *))
 {
 	struct resource res;
-	u64 orig_end;
-	int ret = -1;
 
 	res.start = start;
 	res.end = end;
 	res.flags = flags;
-	orig_end = res.end;
-
-	while ((res.start < res.end) &&
-		(!find_next_iomem_res(&res, desc, false))) {
-
-		ret = (*func)(res.start, res.end, arg);
-		if (ret)
-			break;
-
-		res.start = res.end + 1;
-		res.end = orig_end;
-	}
 
-	return ret;
+	return __walk_iomem_res_desc(&res, desc, false, arg, func);
 }
 
 /*

@@ -451,22 +458,13 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 				int (*func)(u64, u64, void *))
 {
 	struct resource res;
-	u64 orig_end;
-	int ret = -1;
 
 	res.start = start;
 	res.end = end;
 	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
-	orig_end = res.end;
-	while ((res.start < res.end) &&
-		(!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
-		ret = (*func)(res.start, res.end, arg);
-		if (ret)
-			break;
-		res.start = res.end + 1;
-		res.end = orig_end;
-	}
-	return ret;
+
+	return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true,
+				     arg, func);
 }
 
 #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)

@@ -508,6 +506,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
 {
 	return 1;
 }
+
 /*
  * This generic page_is_ram() returns true if specified address is
  * registered as System RAM in iomem_resource list.

@@ -91,11 +91,13 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
  * and that value will be returned. If all free regions are visited without
  * func returning non-zero, then zero will be returned.
  */
-int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *))
+int arch_kexec_walk_mem(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *))
 {
 	int ret = 0;
 	u64 i;
 	phys_addr_t mstart, mend;
+	struct resource res = { };
 
 	if (kbuf->top_down) {
 		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,

@@ -105,7 +107,9 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *))
 			 * range while in kexec, end points to the last byte
 			 * in the range.
 			 */
-			ret = func(mstart, mend - 1, kbuf);
+			res.start = mstart;
+			res.end = mend - 1;
+			ret = func(&res, kbuf);
 			if (ret)
 				break;
 		}

@@ -117,7 +121,9 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *))
 			 * range while in kexec, end points to the last byte
 			 * in the range.
 			 */
-			ret = func(mstart, mend - 1, kbuf);
+			res.start = mstart;
+			res.end = mend - 1;
+			ret = func(&res, kbuf);
 			if (ret)
 				break;
 		}

@@ -209,7 +209,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
+static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
 {
 	unsigned int *nr_ranges = arg;
 

@@ -342,7 +342,7 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
 	return ret;
 }
 
-static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg)
+static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
 {
 	struct crash_elf_data *ced = arg;
 	Elf64_Ehdr *ehdr;

@@ -355,7 +355,7 @@ static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg)
 	ehdr = ced->ehdr;
 
 	/* Exclude unwanted mem ranges */
-	ret = elf_header_exclude_ranges(ced, start, end);
+	ret = elf_header_exclude_ranges(ced, res->start, res->end);
 	if (ret)
 		return ret;
 

@@ -518,14 +518,14 @@ static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 	return 0;
 }
 
-static int memmap_entry_callback(u64 start, u64 end, void *arg)
+static int memmap_entry_callback(struct resource *res, void *arg)
 {
 	struct crash_memmap_data *cmd = arg;
 	struct boot_params *params = cmd->params;
 	struct e820_entry ei;
 
-	ei.addr = start;
-	ei.size = end - start + 1;
+	ei.addr = res->start;
+	ei.size = res->end - res->start + 1;
 	ei.type = cmd->type;
 	add_e820_entry(params, &ei);
 

@@ -619,12 +619,12 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
 	return ret;
 }
 
-static int determine_backup_region(u64 start, u64 end, void *arg)
+static int determine_backup_region(struct resource *res, void *arg)
 {
 	struct kimage *image = arg;
 
-	image->arch.backup_src_start = start;
-	image->arch.backup_src_sz = end - start + 1;
+	image->arch.backup_src_start = res->start;
+	image->arch.backup_src_sz = res->end - res->start + 1;
 
 	/* Expecting only one range for backup region */
 	return 1;

@@ -6,7 +6,7 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 
-static int found(u64 start, u64 end, void *data)
+static int found(struct resource *res, void *data)
 {
 	return 1;
 }

@@ -269,10 +269,10 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *));
 extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
-		    int (*func)(u64, u64, void *));
+		    int (*func)(struct resource *, void *));
 extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
-		    void *arg, int (*func)(u64, u64, void *));
+		    void *arg, int (*func)(struct resource *, void *));
 
 /* True if any part of r1 overlaps r2 */
 static inline bool resource_overlaps(struct resource *r1, struct resource *r2)

@@ -159,7 +159,7 @@ struct kexec_buf {
 };
 
 int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			       int (*func)(u64, u64, void *));
+			       int (*func)(struct resource *, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
 #endif /* CONFIG_KEXEC_FILE */

@@ -406,9 +406,10 @@ static int locate_mem_hole_bottom_up(unsigned long start, unsigned long end,
 	return 1;
 }
 
-static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
+static int locate_mem_hole_callback(struct resource *res, void *arg)
 {
 	struct kexec_buf *kbuf = (struct kexec_buf *)arg;
+	u64 start = res->start, end = res->end;
 	unsigned long sz = end - start + 1;
 
 	/* Returning 0 will take to next memory range */

@@ -437,7 +438,7 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
  * func returning non-zero, then zero will be returned.
  */
 int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			       int (*func)(u64, u64, void *))
+			       int (*func)(struct resource *, void *))
 {
 	if (kbuf->image->type == KEXEC_TYPE_CRASH)
 		return walk_iomem_res_desc(crashk_res.desc,

@@ -403,14 +403,15 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc,
 
 static int __walk_iomem_res_desc(struct resource *res, unsigned long desc,
 				 bool first_level_children_only,
-				 void *arg, int (*func)(u64, u64, void *))
+				 void *arg,
+				 int (*func)(struct resource *, void *))
 {
 	u64 orig_end = res->end;
 	int ret = -1;
 
 	while ((res->start < res->end) &&
 	       !find_next_iomem_res(res, desc, first_level_children_only)) {
-		ret = (*func)(res->start, res->end, arg);
+		ret = (*func)(res, arg);
 		if (ret)
 			break;
 

@@ -436,7 +437,7 @@ static int __walk_iomem_res_desc(struct resource *res, unsigned long desc,
  * <linux/ioport.h> and set it in 'desc' of a target resource entry.
  */
 int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
-		u64 end, void *arg, int (*func)(u64, u64, void *))
+		u64 end, void *arg, int (*func)(struct resource *, void *))
 {
 	struct resource res;
 

@@ -455,7 +456,7 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
  * ranges.
  */
 int walk_system_ram_res(u64 start, u64 end, void *arg,
-				int (*func)(u64, u64, void *))
+				int (*func)(struct resource *, void *))
 {
 	struct resource res;
 

@@ -191,8 +191,86 @@ void __init sme_early_init(void)
 	/* Update the protection map with memory encryption mask */
 	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
 		protection_map[i] = pgprot_encrypted(protection_map[i]);
+
+	if (sev_active())
+		swiotlb_force = SWIOTLB_FORCE;
+}
+
+static void *sme_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		       gfp_t gfp, unsigned long attrs)
+{
+	unsigned long dma_mask;
+	unsigned int order;
+	struct page *page;
+	void *vaddr = NULL;
+
+	dma_mask = dma_alloc_coherent_mask(dev, gfp);
+	order = get_order(size);
+
+	/*
+	 * Memory will be memset to zero after marking decrypted, so don't
+	 * bother clearing it before.
+	 */
+	gfp &= ~__GFP_ZERO;
+
+	page = alloc_pages_node(dev_to_node(dev), gfp, order);
+	if (page) {
+		dma_addr_t addr;
+
+		/*
+		 * Since we will be clearing the encryption bit, check the
+		 * mask with it already cleared.
+		 */
+		addr = __sme_clr(phys_to_dma(dev, page_to_phys(page)));
+		if ((addr + size) > dma_mask) {
+			__free_pages(page, get_order(size));
+		} else {
+			vaddr = page_address(page);
+			*dma_handle = addr;
+		}
+	}
+
+	if (!vaddr)
+		vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);
+
+	if (!vaddr)
+		return NULL;
+
+	/* Clear the SME encryption bit for DMA use if not swiotlb area */
+	if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) {
+		set_memory_decrypted((unsigned long)vaddr, 1 << order);
+		memset(vaddr, 0, PAGE_SIZE << order);
+		*dma_handle = __sme_clr(*dma_handle);
+	}
+
+	return vaddr;
+}
+
+static void sme_free(struct device *dev, size_t size, void *vaddr,
+		     dma_addr_t dma_handle, unsigned long attrs)
+{
+	/* Set the SME encryption bit for re-use if not swiotlb area */
+	if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle)))
+		set_memory_encrypted((unsigned long)vaddr,
+				     1 << get_order(size));
+
+	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
 }
 
+static const struct dma_map_ops sme_dma_ops = {
+	.alloc                  = sme_alloc,
+	.free                   = sme_free,
+	.map_page               = swiotlb_map_page,
+	.unmap_page             = swiotlb_unmap_page,
+	.map_sg                 = swiotlb_map_sg_attrs,
+	.unmap_sg               = swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu    = swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu        = swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device     = swiotlb_sync_sg_for_device,
+	.mapping_error          = swiotlb_dma_mapping_error,
+};
+
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_init(void)
 {

@@ -202,6 +280,14 @@ void __init mem_encrypt_init(void)
 	/* Call into SWIOTLB to update the SWIOTLB DMA buffers */
 	swiotlb_update_mem_attributes();
 
+	/*
+	 * With SEV, DMA operations cannot use encryption. New DMA ops
+	 * are required in order to mark the DMA areas as decrypted or
+	 * to use bounce buffers.
+	 */
+	if (sev_active())
+		dma_ops = &sme_dma_ops;
+
 	pr_info("AMD Secure Memory Encryption (SME) active\n");
 }
 

@@ -507,8 +507,9 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	if (no_iotlb_memory)
 		panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
 
-	if (sme_active())
-		pr_warn_once("SME is active and system is using DMA bounce buffers\n");
+	if (sme_active() || sev_active())
+		pr_warn_once("%s is active and system is using DMA bounce buffers\n",
+			     sme_active() ? "SME" : "SEV");
 
 	mask = dma_get_seg_boundary(hwdev);
 

@@ -69,6 +69,26 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
 	return 0;
 }
 
+static int __ioremap_res_desc_other(struct resource *res, void *arg)
+{
+	return (res->desc != IORES_DESC_NONE);
+}
+
+/*
+ * This function returns true if the target memory is marked as
+ * IORESOURCE_MEM and IORESOURCE_BUSY and described as other than
+ * IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
+ */
+static bool __ioremap_check_if_mem(resource_size_t addr, unsigned long size)
+{
+	u64 start, end;
+
+	start = (u64)addr;
+	end = start + size - 1;
+
+	return (walk_mem_res(start, end, NULL, __ioremap_res_desc_other) == 1);
+}
+
 /*
  * Remap an arbitrary physical address space into the kernel virtual
  * address space. It transparently creates kernel huge I/O mapping when

@@ -146,7 +166,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		pcm = new_pcm;
 	}
 
+	/*
+	 * If the page being mapped is in memory and SEV is active then
+	 * make sure the memory encryption attribute is enabled in the
+	 * resulting mapping.
+	 */
 	prot = PAGE_KERNEL_IO;
+	if (sev_active() && __ioremap_check_if_mem(phys_addr, size))
+		prot = pgprot_encrypted(prot);
+
 	switch (pcm) {
 	case _PAGE_CACHE_MODE_UC:
 	default:

@@ -268,6 +268,9 @@ extern int
 walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *));
 extern int
+walk_mem_res(u64 start, u64 end, void *arg,
+	     int (*func)(struct resource *, void *));
+extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(struct resource *, void *));
 extern int

@@ -468,6 +468,23 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 				     arg, func);
 }
 
+/*
+ * This function calls the @func callback against all memory ranges, which
+ * are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
+ */
+int walk_mem_res(u64 start, u64 end, void *arg,
+		 int (*func)(struct resource *, void *))
+{
+	struct resource res;
+
+	res.start = start;
+	res.end = end;
+	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true,
+				     arg, func);
+}
+
 #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 
 /*

@@ -114,10 +114,11 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_pvti_cpu0_va();
 		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
-			ret = vm_insert_pfn(
+			ret = vm_insert_pfn_prot(
 				vma,
 				vmf->address,
-				__pa(pvti) >> PAGE_SHIFT);
+				__pa(pvti) >> PAGE_SHIFT,
+				pgprot_decrypted(vma->vm_page_prot));
 		}
 	} else if (sym_offset == image->sym_hvclock_page) {
 		struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();

@@ -27,6 +27,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>

@@ -45,7 +46,7 @@ early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
 static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock wall_clock;
+static struct pvclock_wall_clock *wall_clock;
 
 struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
 {

@@ -64,15 +65,18 @@ static void kvm_get_wallclock(struct timespec *now)
 	int low, high;
 	int cpu;
 
-	low = (int)__pa_symbol(&wall_clock);
-	high = ((u64)__pa_symbol(&wall_clock) >> 32);
+	if (!wall_clock)
+		return;
+
+	low = (int)slow_virt_to_phys(wall_clock);
+	high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
 
 	native_write_msr(msr_kvm_wall_clock, low, high);
 
 	cpu = get_cpu();
 
 	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
+	pvclock_read_wallclock(wall_clock, vcpu_time, now);
 
 	put_cpu();
 }

@@ -249,11 +253,39 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
+static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
+					     phys_addr_t align)
+{
+	phys_addr_t mem;
+
+	mem = memblock_alloc(size, align);
+	if (!mem)
+		return 0;
+
+	if (sev_active()) {
+		if (early_set_memory_decrypted(mem, size))
+			goto e_free;
+	}
+
+	return mem;
+e_free:
+	memblock_free(mem, size);
+	return 0;
+}
+
+static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
+{
+	if (sev_active())
+		early_set_memory_encrypted(addr, size);
+
+	memblock_free(addr, size);
+}
+
 void __init kvmclock_init(void)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned long mem;
-	int size, cpu;
+	unsigned long mem, mem_wall_clock;
+	int size, cpu, wall_clock_size;
 	u8 flags;
 
 	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);